Superpixels: An Evaluation of the State-of-the-Art

Abstract

Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives for subsequent processing steps. As of these properties, superpixel algorithms have received much attention since their naming in 2003. By today, publicly available superpixel algorithms have turned into standard tools in low-level vision. As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison. Until now, the rapidly growing number of algorithms as well as varying experimental setups hindered the development of a unifying benchmark. We present a comprehensive evaluation of 28 state-of-the-art superpixel algorithms utilizing a benchmark focussing on fair comparison and designed to provide new insights relevant for applications. To this end, we explicitly discuss parameter optimization and the importance of strictly enforcing connectivity. Furthermore, by extending well-known metrics, we are able to summarize algorithm performance independent of the number of generated superpixels, thereby overcoming a major limitation of available benchmarks. Furthermore, we discuss runtime, robustness against noise, blur and affine transformations, implementation details as well as aspects of visual quality. Finally, we present an overall ranking of superpixel algorithms which redefines the state-of-the-art and enables researchers to easily select appropriate algorithms and the corresponding implementations which themselves are made publicly available as part of our benchmark at davidstutz.de/projects/superpixel-benchmark/.

Cited by in corpus (39)

• Apple Flower Detection using Deep Convolutional Networks
• Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
• Superpixel Contracted Graph-Based Learning for Hyperspectral Image Classification
• A survey of image labelling for computer vision applications
• Fuzzy SLIC: Fuzzy Simple Linear Iterative Clustering
• A comprehensive review and new taxonomy on superpixel segmentation
• Superpixel Segmentation using Dynamic and Iterative Spanning Forest
• Component Segmentation of Engineering Drawings Using Graph Convolutional Networks
• Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks
• Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
• Adaptive strategy for superpixel-based region-growing image segmentation
• Efficient semantic image segmentation with superpixel pooling
• Superpixel Segmentation with Fully Convolutional Networks
• Dynamic Spectral Residual Superpixels
• A Tutorial on Modeling and Inference in Undirected Graphical Models for Hyperspectral Image Analysis
• Geodesic Centroidal Voronoi Tessellations: Theories, Algorithms and Applications
• Part-based Tracking by Sampling
• Hierarchical Homogeneity-Based Superpixel Segmentation: Application to Hyperspectral Image Analysis
• A Spitting Image: Modular Superpixel Tokenization in Vision Transformers
• Saliency-guided Adaptive Seeding for Supervoxel Segmentation
• Power-SLIC: Fast Superpixel Segmentations by Diagrams
• Generating superpixels using deep image representations
• Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
• ISEC: Iterative over-Segmentation via Edge Clustering
• Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing
• Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks
• Active Scene Learning
• Evaluation Framework of Superpixel Methods with a Global Regularity Measure
• Robust superpixels using color and contour features along linear path
• Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching
• Superpixel-Based Background Recovery from Multiple Images
• Unsupervised Community Detection with a Potts Model Hamiltonian, an Efficient Algorithmic Solution, and Applications in Digital Pathology
• Super-Trajectories: A Compact Yet Rich Video Representation
• An ILP Solver for Multi-label MRFs with Connectivity Constraints
• Generating Superpixels for High-resolution Images with Decoupled Patch Calibration
• A novel centroid update approach for clustering-based superpixel methods and superpixel-based edge detection
• Multi-Scale Superpatch Matching using Dual Superpixel Descriptors
• Towards Automated Cadastral Boundary Delineation from UAV Data
• Robust Shape Regularity Criteria for Superpixel Evaluation